API Reference

Create a new model

post
https://api.instill-ai.com/v1alpha/namespaces//models

Creates a new model under the parenthood of a namespace. This is an
asynchronous endpoint, i.e., the server will not wait for the model to be
created in order to respond. Instead, it will return a response with the
necessary information to access the result and status of the creation
operation.

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Path Params
string
required

Namespace ID

Body Params

The properties of the model to be created.

string
required

Model resource ID (used in name as the last segment). This conforms to
RFC-1034, which restricts to letters, numbers, and hyphen, with the first
character a letter, the last a letter or a number, and a 63 character
maximum.

string

Model description.

string
required

The model definition that has been used to import the model.

configuration
object
required

Model configuration. This field is validated against the model
specification in the model definition (i.e. the model_spec field in the
model definition).

string
enum
required

Task enumerates the AI task that a model is designed to solve.

  • TASK_CLASSIFICATION: Image Classification - classify images into predefined categories.
  • TASK_DETECTION: Object Detection - detect and localize multiple objects in images.
  • TASK_KEYPOINT: Keypoint Detection - detect and localize multiple keypoints of objects in images.
  • TASK_OCR: OCR (Optical Character Recognition) - detect and recognize text in images.
  • TASK_INSTANCE_SEGMENTATION: Instance Segmentation - detect, localize and delineate multiple objects in images.
  • TASK_SEMANTIC_SEGMENTATION: Semantic Segmentation - classify image pixels into predefined categories.
  • TASK_TEXT_TO_IMAGE: Text to Image - generate images from input text prompts.
  • TASK_IMAGE_TO_IMAGE: Image to Image - generate an image from another image.
  • TASK_EMBEDDING: Embedding - generate an embedding (a representation as coordinates) from a multimodal input.
  • TASK_SPEECH_RECOGNITION: Speech Recognition - transcribe the words in an audio input.
  • TASK_CHAT: Conversational Text Generation - generate text as responses to a dialog input.
  • TASK_COMPLETION: Completion Text Generation - generate text following the input prompt.
  • TASK_CUSTOM: Custom - custom task type for free form input/output.
string
enum
required

Visibility defines who can access the model.

  • VISIBILITY_PRIVATE: Only the owner can see the model.
  • VISIBILITY_PUBLIC: Other users can see the model.
Allowed:
string
required

Region of choice for the particular provider to host the model.

string
required

Hardware of choice to serve the model.

string

README holds the model documentation.

string

A link to the source code of the model (e.g. to a GitHub repository).

string

A link to any extra information.

string

License under which the model is distributed.

string

Model profile image in base64 format.

Responses

Updated about 1 year ago

Did this page help you?
Language
Credentials
Header
URL
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json

Updated about 1 year ago

Did this page help you?